From b1dce7fa2b1d31af75f9e136c0571fb17f0e3ed9 Mon Sep 17 00:00:00 2001
From: Andreas Roussos <a.roussos@dataly.gr>
Date: Tue, 1 Aug 2023 20:49:55 +0200
Subject: [PATCH] Bug 21828: build $bib_heading_fields only once per invocation

In UNIMARC instances, the run time of link_bibs_to_authorities.pl
can be reduced by up to 80% and the number of DBI calls
can be reduced by up to 90% with a very simple fix that
optimises the constructor of the C4::Heading::UNIMARC object.

Currently, the constructor resets the $bib_heading_fields hash
*in each invocation* (i.e. for every field the bibliographic
record contains), then populating it again with the results
fetched from the database! This is inefficient.

The patch/fix is trivial: we take advantage of the fact that
$bib_heading_fields is declared at the top of the
C4::Heading::UNIMARC module and is thus a package variable
that is in scope for the entire execution of the program
(more info here: https://stackoverflow.com/q/75317862).

Placing the section that generates the $bib_heading_fields
hash inside a "unless ( defined $bib_heading_fields )" code
block is enough to cause a significant reduction in the
number of "expensive" SQL SELECT queries that must be run.

Test plan:

0) Have a UNIMARC instance with some sample data (the KTD one
   will do just fine for this experiment).

1) Run the following commands:

    $ ktd --shell
   k$ DBI_PROFILE=1 ./misc/link_bibs_to_authorities.pl -t

   Observe the output from the script and the DBI profiling info.
   [You may want to play with different DBI_PROFILE levels (such as
   2, 4, 6, 8, etc.) to see what's going on under the hood DBI-wise,
   for reference see: https://metacpan.org/pod/DBI::Profile]

2) Apply this patch.

3) Rerun the script from step 1), it should run a lot faster!
---
 C4/Heading/UNIMARC.pm | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/C4/Heading/UNIMARC.pm b/C4/Heading/UNIMARC.pm
index 9767f751a7..a0a8a3edda 100644
--- a/C4/Heading/UNIMARC.pm
+++ b/C4/Heading/UNIMARC.pm
@@ -68,19 +68,21 @@ my $bib_heading_fields;
 sub new {
     my $class = shift;
 
-    my $dbh = C4::Context->dbh;
-    my $sth = $dbh->prepare(
-        "SELECT tagfield, authtypecode
-         FROM marc_subfield_structure
-         WHERE frameworkcode = '' AND authtypecode <> ''"
-    );
-    $sth->execute();
-    $bib_heading_fields = {};
-    while ( my ( $tag, $auth_type ) = $sth->fetchrow ) {
-        $bib_heading_fields->{$tag} = {
-            auth_type => $auth_type,
-            subfields => 'abcdefghjklmnopqrstvxyz',
-        };
+    unless ( defined $bib_heading_fields ) {
+        my $dbh = C4::Context->dbh;
+        my $sth = $dbh->prepare(
+            "SELECT tagfield, authtypecode
+             FROM marc_subfield_structure
+             WHERE frameworkcode = '' AND authtypecode <> ''"
+        );
+        $sth->execute();
+        $bib_heading_fields = {};
+        while ( my ( $tag, $auth_type ) = $sth->fetchrow ) {
+            $bib_heading_fields->{$tag} = {
+                auth_type => $auth_type,
+                subfields => 'abcdefghjklmnopqrstvxyz',
+            };
+        }
     }
 
     return bless {}, $class;
-- 
2.20.1